Traffic Forecasting using Vehicle-to-Vehicle Communication

Steven Wong, Lejun Jiang, Robin Walters, Tamás G. Molnár, Gábor Orosz, Rose Yu
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:917-929, 2021.

Abstract

Vehicle-to-vehicle (V2V) communication is utilized in order to provide real-time on-board traffic predictions. A hybrid approach is proposed where physics based models are supplemented with deep learning. A recurrent neural network is used to improve the accuracy of predictions given by first principle models. Our hybrid model is able to predict the velocity of individual vehicles up to 40 seconds into the future with improved accuracy over physics based baselines. A comprehensive study is conducted to evaluate different methods of integrating physics with deep learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-wong21a, title = {Traffic Forecasting using Vehicle-to-Vehicle Communication}, author = {Wong, Steven and Jiang, Lejun and Walters, Robin and Moln\'ar, Tam\'as G. and Orosz, G\'abor and Yu, Rose}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {917--929}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/wong21a/wong21a.pdf}, url = {https://proceedings.mlr.press/v144/wong21a.html}, abstract = {Vehicle-to-vehicle (V2V) communication is utilized in order to provide real-time on-board traffic predictions. A hybrid approach is proposed where physics based models are supplemented with deep learning. A recurrent neural network is used to improve the accuracy of predictions given by first principle models. Our hybrid model is able to predict the velocity of individual vehicles up to 40 seconds into the future with improved accuracy over physics based baselines. A comprehensive study is conducted to evaluate different methods of integrating physics with deep learning.} }
Endnote
%0 Conference Paper %T Traffic Forecasting using Vehicle-to-Vehicle Communication %A Steven Wong %A Lejun Jiang %A Robin Walters %A Tamás G. Molnár %A Gábor Orosz %A Rose Yu %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-wong21a %I PMLR %P 917--929 %U https://proceedings.mlr.press/v144/wong21a.html %V 144 %X Vehicle-to-vehicle (V2V) communication is utilized in order to provide real-time on-board traffic predictions. A hybrid approach is proposed where physics based models are supplemented with deep learning. A recurrent neural network is used to improve the accuracy of predictions given by first principle models. Our hybrid model is able to predict the velocity of individual vehicles up to 40 seconds into the future with improved accuracy over physics based baselines. A comprehensive study is conducted to evaluate different methods of integrating physics with deep learning.
APA
Wong, S., Jiang, L., Walters, R., Molnár, T.G., Orosz, G. & Yu, R.. (2021). Traffic Forecasting using Vehicle-to-Vehicle Communication. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:917-929 Available from https://proceedings.mlr.press/v144/wong21a.html.

Related Material